Skip to main content

Table 3 Comparison of ATMs. Compared with SENet and CBAM, our model had better performance in accuracy, sensitivity, AUC, and F1-score

From: Effective automatic detection of anterior cruciate ligament injury using convolutional neural network with two attention mechanism modules

Model

Accuracy

Precision

Sensitivity

Specificity

AUC

F1-score

SENet

0.7905

0.8005

0.8366

0.7309

0.8646

0.8128

CBAM

0.8127

0.8496

0.8113

0.8145

0.8842

0.8300

ATM1

0.8111

0.8041

0.8789

0.7236

0.8786

0.8398

ATM2

0.7667

0.8824

0.6761

0.8836

0.8831

0.7656

Ours

0.8063

0.7741

0.9268

0.6509

0.8886

0.8436

Back to article page

BMC Medical Imaging

ISSN: 1471-2342

Contact us